Labira/LabiraPJOK_1_100

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0026
• Validation Loss: 8.2710
• Epoch: 94

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 300, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.5573	6.1112	0
0.2525	4.7174	1
0.4330	4.9959	2
0.2496	5.5703	3
0.1868	5.9061	4
0.1491	6.0854	5
0.1951	6.3417	6
0.0492	6.4913	7
0.0296	6.5959	8
0.0352	6.7091	9
0.0530	6.7985	10
0.0265	6.9577	11
0.0239	7.1006	12
0.0221	7.2133	13
0.0171	7.3099	14
0.0154	7.4198	15
0.0089	7.5009	16
0.0268	7.4562	17
0.0150	7.4317	18
0.0153	7.4442	19
0.0076	7.4628	20
0.0137	7.5225	21
0.0186	7.5907	22
0.0078	7.6655	23
0.0087	7.7399	24
0.0074	7.8006	25
0.0082	7.8462	26
0.0113	7.8900	27
0.0092	7.9273	28
0.0075	7.9621	29
0.0066	8.0058	30
0.0061	8.0359	31
0.0058	8.0681	32
0.0043	8.0693	33
0.0058	8.0939	34
0.0066	8.0860	35
0.0065	8.0647	36
0.0040	8.0451	37
0.0039	8.0354	38
0.0050	8.0227	39
0.0033	8.0230	40
0.0049	8.0296	41
0.0055	8.0414	42
0.0042	8.0576	43
0.0035	8.0749	44
0.0041	8.0896	45
0.0032	8.1037	46
0.0037	8.1187	47
0.0038	8.1324	48
0.0040	8.1458	49
0.0046	8.1626	50
0.0028	8.1726	51
0.0061	8.1180	52
0.0043	8.0579	53
0.0032	8.0223	54
0.0029	8.0125	55
0.0068	8.0192	56
0.0034	8.0336	57
0.0044	8.0478	58
0.0025	8.0648	59
0.0026	8.0813	60
0.0031	8.0949	61
0.0024	8.1060	62
0.0030	8.1093	63
0.0051	8.1350	64
0.0046	8.1498	65
0.0057	8.1556	66
0.0030	8.1641	67
0.0038	8.1758	68
0.0040	8.1901	69
0.0027	8.2013	70
0.0036	8.2115	71
0.0055	8.2151	72
0.0025	8.2120	73
0.0026	8.2121	74
0.0036	8.2132	75
0.0031	8.2141	76
0.0023	8.2159	77
0.0036	8.2201	78
0.0032	8.2284	79
0.0025	8.2278	80
0.0030	8.2375	81
0.0028	8.2451	82
0.0023	8.2491	83
0.0073	8.2581	84
0.0035	8.2639	85
0.0024	8.2646	86
0.0031	8.2628	87
0.0036	8.2641	88
0.0025	8.2660	89
0.0031	8.2669	90
0.0047	8.2678	91
0.0021	8.2687	92
0.0023	8.2698	93
0.0026	8.2710	94

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 3.0.1
• Tokenizers 0.19.1